Copyright © 2026 Authors retain the copyright of this article. This article is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

@article{199439,
        author = {CEENA MATHEWS},
        title = {An Explainable ResNet50-Based Framework for Paddy Crop Disease Detection Using Grad-CAM in Precision Agriculture},
        journal = {International Journal of Innovative Research in Technology},
        year = {2026},
        volume = {12},
        number = {11},
        pages = {12884-12889},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=199439},
        abstract = {The early and accurate detection of crop diseases is essential for improving agricultural productivity and ensuring global food security, particularly in staple crops such as rice. In this study, an explainable deep learning framework based on ResNet50 is proposed for classifying paddy crop diseases. The model is trained and evaluated on a real-world dataset comprising ten classes, including healthy leaves. Transfer learning is employed by initializing the network with pretrained ImageNet weights, followed by fine-tuning to enhance classification performance. The proposed model achieves a validation accuracy of 90.53% and a weighted F1-score of 0.905, indicating robust performance across classes. To address the lack of interpretability in deep learning models, Gradient-weighted Class Activation Mapping (Grad-CAM) is integrated to generate visual explanations of model predictions. The experimental results demonstrate that the model effectively focuses on disease-affected regions in leaf images, thereby validating its decision-making process. The proposed framework provides a balance between high accuracy and interpretability, making it suitable for real-world deployment in precision agriculture systems.},
        keywords = {Explainable AI, Grad-CAM, Resnet-50},
        month = {April},
        }